Recent advances in Large Audio Language Models (LALMs) have extended Text-to-Speech (TTS) to interactive role-play scenarios, which demand high expressiveness and strict adherence to role-play instructions. However, existing models struggle to maintain stylistic consistency with character profiles and scene descriptions across multi-turn dialogues. A critical bottleneck is the lack of objective metrics for quantifying speaking style. To bridge this gap, we propose Mean Continuation Log-Probability (MCLP) as both an evaluation metric and a reward signal, validated on LALM-based Role-Play TTS (RP-TTS) tasks. MCLP leverages the in-context learning capability of pretrained LALMs to measure the likelihood of ground-truth speech tokens conditioned on a contextual history consisting of the transcript, generated speech, and repeated transcript, serving as a proxy for stylistic continuity. Furthermore, we employ MCLP as a reinforcement learning reward to enhance the style alignment between generated speech and role-play instructions. To support this task, we construct a large-scale RP-TTS dataset with rich scene and character annotations. Experiments demonstrate that MCLP is well aligned with human judgments of stylistic consistency and serves as an effective reward for improving RP-TTS, leading to consistent gains in both objective metrics and subjective evaluations. Our code is publicly available at https://github.com/y-ren16/MCLP.

翻译：近期大型音频语言模型（LALMs）的进展已将文本转语音（TTS）扩展至需要高表现力与严格遵循角色扮演指令的交互式场景。然而，现有模型在多轮对话中难以保持与角色设定及场景描述一致的风格稳定性，其关键瓶颈在于缺乏量化说话风格的客观指标。为弥合这一差距，我们提出将平均延续对数概率（MCLP）同时作为评估指标与奖励信号，并在基于LALM的角色扮演文本转语音（RP-TTS）任务上验证其有效性。MCLP利用预训练LALMs的上下文学习能力，通过计算真实语音令牌在包含文本转录、生成语音及重复转录组成的上下文历史条件下的似然性，来衡量风格连续性的代理指标。此外，我们将MCLP作为强化学习奖励信号，以增强生成语音与角色扮演指令之间的风格对齐。为支持该任务，我们构建了包含丰富场景与角色标注的大规模RP-TTS数据集。实验表明，MCLP与人类对风格一致性的判断高度吻合，并可作为提升RP-TTS的有效奖励机制，在客观指标与主观评估中均带来持续改进。我们的代码已开源至https://github.com/y-ren16/MCLP。